{"id":"W4416322339","doi":"10.3390/make7040148","title":"Model-Aware Automatic Benchmark Generation with Self-Error Instructions for Data-Driven Models","year":2025,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministero dello Sviluppo Economico","keywords":"Benchmark (surveying); Data point; Generative grammar; Regression; Data-driven; Data modeling; Experimental data","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005090389,0.0002060386,0.0001977429,0.0002774961,0.0008348008,0.0003011975,0.0003980484,0.00010854,0.000004713109],"category_scores_gemma":[0.00009843458,0.000182175,0.00003304933,0.0004043256,0.00002953461,0.001333411,0.0001885927,0.0004219944,0.000006190362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007296129,"about_ca_system_score_gemma":0.0001822992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005477871,"about_ca_topic_score_gemma":0.000209203,"domain_scores_codex":[0.9984859,0.0001715463,0.0002841524,0.0006965277,0.0001439799,0.0002178789],"domain_scores_gemma":[0.9988374,0.0001493316,0.000179841,0.0005974428,0.0001639918,0.00007198029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004205169,0.000439043,0.00315335,0.000401274,0.0001673961,0.000001761549,0.001708139,0.2533523,0.001428478,0.05965323,0.003024453,0.6766285],"study_design_scores_gemma":[0.0005573839,0.00008923175,0.0005044761,0.00004750417,0.00006453277,0.00002684896,0.00003852599,0.9834656,0.00002546244,0.0007219054,0.01426125,0.0001973572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007585726,0.0003359425,0.986616,0.0008695757,0.0003276286,0.0003201941,0.00001660882,0.0006453958,0.00328291],"genre_scores_gemma":[0.8378218,0.00006873941,0.1589284,0.00003266144,0.0001084215,0.00008683692,0.0008175698,0.00001695642,0.002118618],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.830236,"threshold_uncertainty_score":0.7428883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05107415529911185,"score_gpt":0.3329024960587661,"score_spread":0.2818283407596542,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}